© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35985
    Prev
    Next
    INDEX
    Explanations

    muddy type, water, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ات
    0.86
    к
    0.79
    ות
    0.78
    .
    0.78
    ї
    0.77
    є
    0.75
    ะ
    0.71
    ى
    0.70
    ان
    0.68
    ле
    0.67
    POSITIVE LOGITS
    miktar
    0.72
    ಬ್ಬಿಣ
    0.72
     Concrete
    0.70
     ön
    0.70
    唃
    0.69
    concrete
    0.69
     emailing
    0.68
     三
    0.67
     إيران
    0.66
    鎿
    0.66
    Activations Density 0.003%

    No Known Activations